CtrlK
BlogDocsLog inGet started
Tessl Logo

twenty-partner-design-doc

Use when turning a qualified Twenty lead — a call-summary brief plus any client braindump/docs — into a partner brief a partner can scope and quote from. Trigger when pointed at a lead folder (e.g. partners-experience/<LEAD>/) and asked to "draft a design doc", "create a partner brief", "translate this into Twenty terms", "scope this for a partner", or "prep the partner handoff". Default output is zero-inference (only what the client said; empty sections get a placeholder). Pass --full for inference mode. Chains after twenty-lead-intro-call-summary.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-sequenced, actionable wrapper with strong validation checkpoints and lean prose. Progressive disclosure is slightly undercut by the missing doctrine bundle file and heavy inline rules that duplicate what the reference should hold.

Suggestions

Ensure design-doc-doctrine.md ships in the bundle so the repeatedly-referenced doctrine file actually exists, or fold the essential rules inline and stop pointing to an absent file.

Move the lengthy Step 7 self-check and Step 8 sub-bullets into design-doc-doctrine.md and keep SKILL.md's steps as concise pointers, reducing duplication between the wrapper and the doctrine.

Confirm the worked-example reference (partners-experience/TSF/...) and any 'Phase 2' plans earn their tokens in the main skill file versus living in the doctrine or notes.

DimensionReasoningScore

Conciseness

Lean wrapper that assumes Claude's competence and delegates the doctrine to a referenced file; no padding or explanation of concepts Claude already knows.

3 / 3

Actionability

Gives executable specifics: a docx extraction command, exact save filenames, a 12-section structure pointer, and WebFetch/AskUserQuestion tool usage per step.

3 / 3

Workflow Clarity

Eight clearly sequenced steps with an explicit self-check validation checkpoint in Step 7 (em dash, bare ~, Source column, stray emoji, renumbering gaps) and feedback to fix-then-save.

3 / 3

Progressive Disclosure

Appropriately splits the doctrine into a referenced design-doc-doctrine.md, but that file is not present in the bundle and the body also embeds substantial inline detail (Step 7 self-check, Step 8 sub-structure) that belongs in the referenced file.

2 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, trigger-rich, and clearly delineates what and when. Third person is maintained throughout, and it distinguishes default vs --full behavior explicitly.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'turning a qualified Twenty lead ... into a partner brief', 'Default output is zero-inference', 'Pass --full for inference mode', and explicit chaining 'Chains after twenty-lead-intro-call-summary'.

3 / 3

Completeness

Explicitly answers both what (turns lead materials into a partner-design-doc/partner brief in Twenty terms) and when ('Trigger when pointed at a lead folder ... and asked to ...').

3 / 3

Trigger Term Quality

Provides natural trigger phrasing a user would say: 'draft a design doc', 'create a partner brief', 'translate this into Twenty terms', 'scope this for a partner', 'prep the partner handoff'.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and domain-specific (Twenty leads → partner briefs), with distinct triggers and explicit chaining from twenty-lead-intro-call-summary, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
twentyhq/twenty
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.